2-nd Workshop on Explainable and Ethical AI – ICPR 2022

XAIE

August 21- 25, 2022
 

XAIE is a workshop of ICPR 2022. It is the followup of the EDL-AI workshop that was held in ICPR 2020.

Call for papers

About

We are witnessing the emergence of an “AI economy and society” where AI technologies are increasingly impacting many aspects of business as well as everyday life. We read with great interest about recent advances in AI medical diagnostic systems, self-driving cars, ability of AI technology to automate many aspects of business decisions like loan approvals, hiring, policing etc. However, as evident by recent experiences, AI systems may produce errors, can exhibit overt or subtle bias, may be sensitive to noise in the data, and often lack technical and judicial transparency and explainability. These shortcomings have been documented in scientific but also and importantly in general press (accidents with self-driving cars, biases in AI-based policing, hiring and loan systems, biases in face recognition systems for people of color, seemingly correct medical diagnoses later found to be made due to wrong reasons etc.). These shortcomings are raising many ethical and policy concerns not only in technical and academic communities, but also among policymakers and general public, and will inevitably impede wider adoption of AI in society.

The problems related to Ethical AI are complex and broad and encompass not only technical issues but also legal, political and ethical ones. One of the key component of Ethical AI systems is explainability or transparency, but other issues like detecting bias, ability to control the outcomes, ability to objectively audit AI systems for ethics are also critical for successful applications and adoption of AI in society. Consequently, explainable and Ethical AI are very current and popular topics both in technical as well as in business, legal and philosophy communities. Many workshops in this field are held at top conferences, and we believe ICPR has to address this topic broadly and focus on its technical aspects. Our proposed workshop aims to address technical aspects of explainable and ethical AI in general, and include related applications and case studies with the aim to address this very important problems from a broad technical perspective.

Topics

The topics comprise but are not limited to:

Program Comittee

Program

We are back to the morning session of ICPR workshop. Here is the scheddule. It may slightly changes depending on local constraints.

09:00-09:30. Opening session.

09:30-10:30. 1st session of long papers - 15+5 min

  1. Romain Xu-Darme, Georges Quenot, Zakaria Chihani and Marie-Christine Rousset, “PARTICUL: Part Identification with Confidence measure using Unsupervised Learning”
  2. Peiyu Li, Soukaina Filali Boubrahimi and Shah Muhammad Hamdi, “Motif-Guided Time Series Counterfactual Explanations”
  3. Tristan Gomez, Thomas Fréour and Harold Mouchère, “Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study”

10:30-10:40. Short paper - 7+3 min

  1. Gianluigi Lopardo and Damien Garreau, “Comparing Feature Importance and Rule Extraction for Interpretability on Text Data”

10:40-11:00. Pause

11:00-12:00. 2nd session of long papers - 15+5 min

  1. Korlan Rysbayeva, Romain Giot and Nicholas Journet, “Graph-based Analysis of Hierarchical Embedding Generated by Deep Neural Network”
  2. Courtney Ford and Mark T. Keane, “Explaining Classifications to Non-Experts: An XAI User Study of Post-Hoc Explanations for a Classifier When People Lack Expertise”
  3. Pierre Dardouillet, Alexandre Benoit, Emna Amri, Philippe Bolon, Dominique Dubucq and Anthony Credoz, “Explainability of Image Semantic Segmentation Through SHAP Values”

12:00-12:30. Invited talk Carlos Toxtli, ““Artificial Intelligence Tools to Promote Social Good in the Workplace”

12:30-13:00: Closing session

Paper submission

A paper can be submitted via the EasyChair online submission system at the following address: https://easychair.org/my/conference?conf=xaie2022.

Paper guidelines

The Proceedings of the XAIE 2022 workshop will be published in the Springer Lecture Notes in Computer Science (LNCS) series. Papers will be selected by a single blind (reviewers are anonymous) review process. Submissions must be formatted in accordance with the Springer’s Computer Science Proceedings guidelines . Two types of contribution will be considered:

Articles should be prepared according to the LNCS author guidelines and templates. All papers must be submitted in electronic format as PDF files before the submission deadline.

Important dates

These dates are still subject to changes.

Workshop organizers